verify-feature

Warn

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill dynamically executes shell commands retrieved from docs/agents/stack.md and docs/agents/quality-gates.md (specifically stack.commands.* and dup_check.cmd). This behavior allows the execution of arbitrary code defined within the repository's documentation files.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it treats content from repository documentation as authoritative instructions for command execution without sanitization.
  • Ingestion points: docs/agents/stack.md and docs/agents/quality-gates.md (referenced in SKILL.md).
  • Boundary markers: Absent. The skill does not use delimiters or provide instructions to the agent to ignore potentially malicious commands embedded in the data.
  • Capability inventory: Arbitrary shell command execution and environment inspection via git diff.
  • Sanitization: Absent. The skill instructs the agent to execute commands directly as defined in the configuration files without validation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 11, 2026, 04:41 PM
Security Audit — agent-trust-hub — verify-feature